ONNX-YOLOv7-Object-Detection
barracuda-release
ONNX-YOLOv7-Object-Detection | barracuda-release | |
---|---|---|
2 | 1 | |
182 | 555 | |
- | 1.4% | |
0.0 | 3.6 | |
about 1 year ago | 10 months ago | |
Python | C# | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ONNX-YOLOv7-Object-Detection
-
[D] Extracting the class labels and bounding boxes for objects, from a YOLO7 model after converting to an ONNX model
Finally, I tried to look if someone has done similar work for the ONNX model and I found this repo which links the same repo I am trying to use, and I believe this function is doing exactly what I want to do, but I could not understand what it is doing (I don't understand how it knows exactly where the number of detections is, and where the bounding boxes are and the class labels, etc.) furthermore, I am not sure if removing end2end and the changing the version from 12 to 9 has any effect on the output shape or it has to do with the internal layers.
-
YOLOv7 object detection in Ruby in 10 minutes
git clone https://github.com/ibaiGorordo/ONNX-YOLOv7-Object-Detection.git cd ONNX-YOLOv7-Object-Detection pip install -r requirements.txt
barracuda-release
-
[D] Extracting the class labels and bounding boxes for objects, from a YOLO7 model after converting to an ONNX model
I removed --end2end from the export flags, which removed the warning, and for the Resize warning I followed the advice on a similar issue
What are some alternatives?
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
netron - Visualizer for neural network, deep learning and machine learning models
yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
onnxruntime-ruby - Run ONNX models in Ruby
models - A collection of pre-trained, state-of-the-art models in the ONNX format
AS-One - Easy & Modular Computer Vision Detectors and Trackers - Run YOLO-NAS,v8,v7,v6,v5,R,X in under 20 lines of code.
blink-morse - Computer vision application to type based on detection of eyes blinking morse code.
play-game-with-computer-vision - A simple python bot (powered by computer vision) used to play a game (City Island 5). The bot is able to play the game and collect points without any human intervention.
qr-measure - Measuring with computer vision
yolov7-pose-estimation - YOLOv7 Pose estimation using OpenCV, PyTorch
yolo-v4-tf.keras - A simple tf.keras implementation of YOLO v4